Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
26
The proposed PRISM (Predictive Representation of Interaction Style and Motion), a framework that infers interaction traits from passive observations of human-human interactions, suggests the utility of passive latent-trait inference for social navigation in dynamic crowds.
The results show that work-aware policy optimization can suppress physically inefficient motion without requiring an explicit differentiable dynamics model.
2D motion inputs can rival 3D data in performance, unlocking new possibilities for real-world applications of Motion Language Models without the need for extensive retraining.
Detecting who is paying attention is now more accurate, thanks to a new method that jointly infers group membership and shared attention.
